141 papers
This paper introduces a novel Speech Generation Speaker Poisoning (SGSP) framework to address privacy risks in zero-shot text-to-speech by modifying trained models to prevent the generation of specific speaker identities while maintaining utility for others, demonstrating effective protection for up to 15 speakers but revealing scalability challenges with larger sets due to identity overlap.
This paper evaluates the trade-off between privacy and Parkinson's disease detection in anonymized speech, demonstrating that while STT-TTS anonymization severely degrades diagnostic performance by erasing prosodic cues, kNN-VC effectively preserves macro-prosodic features to maintain high detection accuracy with only a minor performance drop.
This paper introduces VASR, a multimodal reasoning framework for Context-Aware Visual Speech Recognition (CAVSR) that leverages an Audio-Visual Chain-of-Thought (AV-CoT) to explicitly ground acoustic signals with rich visual context like scenes and on-screen text, thereby overcoming single-modality dominance and achieving state-of-the-art performance.
This paper introduces a comprehensive multimodal dataset comprising audio and vibration signals from a single-speed chain conveyor system, designed to benchmark robust industrial fault detection and classification under diverse operating conditions and noise levels through standardized evaluation protocols and baseline models.
This paper introduces a mechanistic interpretability approach to identify "audio-specialist" attention heads in large audio-language models, enabling a parameter-free inference-time steering technique that significantly boosts audio grounding and accuracy by amplifying the model's reliance on audio evidence.
This paper introduces Task 5 of the DCASE 2025 Challenge, a multi-domain Audio Question Answering benchmark designed to evaluate and advance the acoustic reasoning capabilities of audio-language models across diverse scenarios including bioacoustics, temporal soundscapes, and complex real-world clips.
This paper presents an optimized version of X-Codec-2.0 that reduces the latent rate to 25 Hz and increases the sampling rate to 24 kHz through simple architectural adjustments, achieving superior multilingual speech quality and efficiency compared to the original baseline.
DualTurn is a dual-channel generative speech model that learns natural turn-taking dynamics through unsupervised pretraining on conversational audio and fine-tuning to predict agent actions, outperforming existing methods in both action prediction accuracy and turn-boundary anticipation while enabling tool-calling capabilities.
This paper introduces Nw\=ach\=a Mun\=a, the first manually transcribed Devanagari speech corpus for the endangered Nepal Bhasha, and demonstrates that proximal cross-lingual transfer from Nepali achieves competitive automatic speech recognition performance comparable to large multilingual models while being significantly more computationally efficient.
The paper introduces ECHO, a novel foundation model that leverages band-split architecture and frequency positional embeddings to achieve state-of-the-art performance in anomaly detection and fault classification across variable-length, arbitrary sampling rate machine signals without requiring padding or cropping.
BemaGANv2 is an advanced GAN-based vocoder that enhances long-term audio generation for Text-to-Music and Text-to-Audio applications by integrating Anti-aliased Multi-Periodicity composition modules in the generator and systematically evaluating novel discriminator combination strategies, including the Multi-Envelope Discriminator, to achieve high-fidelity and temporally coherent results.
This paper introduces Trilobyte, a byte-level tokenization schema that enables tractable lossless compression of full-fidelity (up to 24-bit) audio using autoregressive language models, demonstrating that while these models outperform FLAC at lower bit depths, their compression gains diminish as bit depth increases.
FoleyFlow introduces a novel video-to-audio generation framework that achieves superior semantic and rhythmic synchronization by aligning unimodal encoders through masked audio-visual modeling and employing a dynamic conditional flow that utilizes temporally varying video features to guide audio synthesis.
This paper introduces an analysis-driven framework that generates a publicly available, 19-hour procedural engine sound dataset with sample-accurate RPM and torque annotations by extracting harmonic structures from real recordings to drive a parametric synthesizer, thereby addressing the scarcity of clean, standardized audio data for automotive sound design and machine learning applications.
This paper proposes a lightweight, self-supervised framework that augments a frozen speech enhancement backbone with low-rank adapters, enabling efficient on-device adaptation to dynamic real-world noise conditions by updating fewer than 1% of parameters while achieving significant signal quality improvements.
This paper proposes a fast and flexible Vocos-based bandwidth extension model that generates missing high-frequency audio content up to 48 kHz using a single neural network and a lightweight refiner, achieving competitive quality with extreme real-time throughput on both GPU and CPU hardware.
This study presents an automated pipeline using a wearable SonicGuard sensor and a pretrained Audio Spectrogram Transformer to accurately segment and classify bowel sounds, significantly reducing manual labeling time while providing clinicians with an objective, quantitative tool for assessing gastrointestinal function.
This paper proposes a method that leverages Multimodal Large Language Models to adaptively and rapidly discover interpretable audio attributes within the AdaFlock framework, achieving superior low-resource classification performance compared to direct MLLM prediction and human-driven approaches in under 11 minutes.
The paper introduces Dolphin, an efficient audio-visual speech separation model that utilizes a dual-path lightweight video encoder with discrete lip semantics and a multi-scale global-local attention mechanism to achieve state-of-the-art separation quality while significantly reducing computational costs and inference time.
This paper proposes a training-free, multi-step inference method for target speaker extraction that iteratively refines speech estimates using a frozen pretrained model and introduces joint metric optimization to balance performance across intrusive and non-intrusive evaluation criteria.